Machine learning compression

Research group on the applications of machine learning to compression

Seminar: “Graph-Convolutional Neural Networks” by Dr. Diego Valsesia

We are glad to announce the next Seminar of the ML-Compr study group: “Graph-Convolutional Neural Networks”  by Dr. Diego Valsesia (Politecnico di Torino, Italy) on the 7th of March at 10h00, Télécom Paristech, 46 rue Barrault (room to be announced).


Convolutional neural networks (CNNs) have enjoyed great success in tasks such as image classification, object detection, etc thanks to weight sharing, invariances to geometric transformations and hierarchical decompositions induced by the convolution operations. However, many data types of interest such as interactions in social networks, 3D point clouds, biological data, etc. do not lie on regular grids like images do and are better represented by graphs. A graph signal has scalar or vector information on every node and edges describe relationships among nodes. Extending the notion of convolution to this kind of signals creates a new building block called graph convolution that can be used in neural networks to solve new problems. Graph-convolutional neural networks are a hot research topic and have been shown to be state-of-the-art for problems such as fake news detection, link prediction in networks, point cloud classification and generation that are badly suited for traditional convolution. Latest research is also showing that graph convolution can improve upon classic convolution even for more traditional problems such as image segmentation and denoising. This lecture will introduce concepts from graph signal processing to present the approaches to define graph-convolutional neural networks. It will then present their application to supervised, semi-supervised and unsupervised problems.

Supplementary material:

The slides of the presentation are available in PDF format at this link.